Multiscale Financial Data Analytics and Machine Learning offers a systematic and comprehensive study on the multiscale approach to financial data analytics and machine learning. This book covers an array of multiscale methods to discover the properties of various timescales embedded in a financial time series, including noise-assisted empirical mode decomposition methods. Important interpretable multiscale outputs from the estimation are recognized as a new set of features that can be used for machine learning. The feature selection problem for machine learning is examined in this volume.This book offers an applied quantitative approach that combines novel analytical methodologies and practical applications to a wide array of examples with real-world data. It is self-contained and organized in its presentation. The explanations of the methodologies are both accessible and detailed enough to capture the interest of the curious student or researcher. Step-by-step descriptions of the algorithms are provided for straightforward implementation.